| { | |
| "_name_or_path": "ibm-fms/Bamba-9B", | |
| "architectures": [ | |
| "BambaForCausalLM" | |
| ], | |
| "attention_bias": false, | |
| "attention_dropout": 0.0, | |
| "attn_layer_indices": [ | |
| 1 | |
| ], | |
| "attn_rotary_emb": 4, | |
| "bos_token_id": 128000, | |
| "eos_token_id": 128001, | |
| "hidden_act": "silu", | |
| "hidden_size": 16, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 32, | |
| "mamba_chunk_size": 256, | |
| "mamba_conv_bias": true, | |
| "mamba_d_conv": 4, | |
| "mamba_d_head": 8, | |
| "mamba_d_state": 8, | |
| "mamba_dt_rank": 256, | |
| "mamba_expand": 4, | |
| "mamba_n_groups": 1, | |
| "mamba_n_heads": 8, | |
| "mamba_proj_bias": false, | |
| "max_position_embeddings": 262144, | |
| "mlp_bias": false, | |
| "model_type": "bamba", | |
| "num_attention_heads": 2, | |
| "num_hidden_layers": 2, | |
| "num_key_value_heads": 1, | |
| "num_logits_to_keep": 1, | |
| "pad_token_id": 0, | |
| "partial_rotary_factor": 0.5, | |
| "rms_norm_eps": 1e-05, | |
| "rope_scaling": null, | |
| "rope_theta": 10000.0, | |
| "tie_word_embeddings": false, | |
| "torch_dtype": "bfloat16", | |
| "transformers_version": "4.48.0", | |
| "use_cache": true, | |
| "use_mamba_kernels": true, | |
| "vocab_size": 128256 | |
| } | |